Intrusion Detection for Marine Meteorological Sensor Network

The rapid development of intelligent devices and wireless communication has greatly promoted the intelligence of the maritime Internet of Things (MIoT) in recent years, and the marine meteorological sensor network (MMSN) is an essential part of MIoT, providing accurate meteorological data for MIoT services. However, the frequent information interaction between the device and the external world also causes information leakage risks for MMSN. Intrusion detection technology based on deep learning is an effective defensive mechanism. Thus, we propose a lightweight one-dimensional convolutional neural network (LCNN) intrusion detection model to adapt to the MMSN environment characteristics and device heterogeneity. In addition, an improved supervised adversarial autoencoder (ISAAE) is proposed for synthesizing samples to address the problem that minority class attack samples are difficult to collect and detect. Finally, the simulation experimental results on the NSL-KDD dataset verify the effectiveness of the proposed method.